Fast visualization tool for large-scale and high dimensional single-cell data

Loom is an AI harness, that can be used with local or cloud LLMs, for complex tasks. It decomposes work, drives execution through a verification harness, and keeps models on track with structured state instead of history. It can route between thinking and acting models, verifies outputs, and exposes an APP/TUI/API/CLI/MCP for both humans & agents.

This project has scripts to set up, build and test installation of AMD ROCm MIVisionX

MCP server exposing 58 tools for Loom's GraphQL API. Works with Claude, Cursor, or any MCP client.

LLMs can't watch videos. vidwise gives them eyes. Extract transcripts, frames, and visual guides from any video.

Scraping contents and taking video with loom

Run AI agents locally with built-in governance and verifiable proof. Loom + Kernel + Intelligence.

Loom: an AST-first, strongly typed language prototype optimized for LLM automation and deterministic patching

MCP server for Loom video management